Anthropic: Claude Sonnet 5 vs. Tencent: Hy3
Direkter Head-to-Head-Vergleich zweier Frontier-Modelle. Tencent: Hy3 gewinnt 3 von 8 Disziplinen.
Letzte Synchronisation:
|
Anthropic: Claude Sonnet 5
Anthropic
Mehr von Anthropic →
|
Tencent: Hy3
Tencent
Mehr von Tencent →
|
|
|---|---|---|
| Quality Index | 41,7 ★ | 33,6 |
| Speed (Tokens/s) | 0 | 189,9 ★ |
| Latency (TTFT) | 0 ms ★ | 1,79 s |
| Preis Input (USD/1M) | $2.00 | $0.123 ★ |
| Preis Output (USD/1M) | $10.00 | $0.43 ★ |
| Context Window | — | — |
| Modalitäten | text | text |
| Release | 06/2026 | 04/2026 |
Anthropic: Claude Sonnet 5
Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...
Tencent: Hy3
Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...